Development of a TVF-EMD-based multi-decomposition technique integrated with Encoder-Decoder-Bidirectional-LSTM for monthly rainfall forecasting

Jamei, Mehdi; Ali, Mumtaz; Malik, Anurag; Karbasi, Masoud; Rai, Priya; Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬, Zaher Mundher

doi:10.1016/j.jhydrol.2023.129105

Cited by 20 publications

(7 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the hyperparameters in hybrid models must be appropriately tuned to avoid overfitting while obtaining the optimal modeling results. To this end, various free-source strategies such as grid search, random search, and Bayesian optimization can be applied and implemented in various programming languages such as MATLAB and Python 60 , 61 . In this research, the ML model is optimized using the grid search technique.…”

Section: Methodsmentioning

confidence: 99%

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm

Karbasi,

Ali,

Bateni

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches—multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012–2018) were used as a training set, and 3 years (2019–2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3–10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

show abstract

Section: Methodsmentioning

confidence: 99%

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm

Karbasi,

Ali,

Bateni

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The RF model, initially proposed by Breiman [36], offers several advantages for remote sensing applications [40], [41]. Widely popular in machine learning programming, the RF algorithm is renowned for its high accuracy in image classification.…”

Section: Google Earth Engine (Gee) and Random Forest Modelmentioning

confidence: 99%

Mapping Forest Fire-affected Areas Using Advanced Machine Learning Techniques in Damoh District of Central India

Moharir,

Manpreet Singh,

Pande

et al. 2024

Kbes

View full text Add to dashboard Cite

Forest fires can cause calamitous damage to the forest ecosystems and may affect climatic parameters, such as temperature, evapotranspiration, and precipitation by catalyzing changes in the local ecology of the region. The main research objective of this work was to quantify the different indices as well as to identify the changes in years 2011 and 2020 in pre- and post-fire, these parameters, such as Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST) and Normalized Burn Ratio Index (NBR), associated with the severity of forest fires in the Damoh district of Madhya Pradesh. An attempt has been also made to understand the interrelationship of these parameters to gauge how these may correlate to determine the sensitivity to forest fires. In this context, we have incorporated advanced GIS methods for the identification of the pre-post fires for 2011 and 2020 year from Landsat 5 and Landsat 8 OLI/TIRS level -1 and Random Forest (RF) model in the Google Earth Engine (GEE) platform. Land Use Land Cover (LULC) map was categorized into five classes based on the satellite data sets. Our findings indicate elevated Land Surface Temperature (LST) values in the Northern and Central regions of the study area, reaching 32.0°C before the fire event. Subsequently, following the fire incident in the year 2011, LST escalated to 39.0°C. Similarly, in the southern and south-eastern regions of the Damoh district, LST peaked at approximately 43.0°C coinciding with the onset of a forest fire in 2020. Furthermore, our analysis revealed a negative correlation between the Normalized Difference Vegetation Index (NDVI) and LST, whereas the Normalized Burn Ratio (NBR) displayed a positive correlation with LST. These results underscore the impact of LST on forest vegetation dynamics, with LST nearing 39.0°C indicating an increased risk of forest fires. The results of this study can be used by local administration to devise an efficient policy related to forest fire management.

show abstract

“…Notably, the hyperparameters in hybrid models must be appropriately tuned to avoid overfitting while obtaining the optimal modeling results. To this end, various free-source strategies such as grid search, random search, and Bayesian optimization can be applied and implemented in various programming languages such as MATLAB and Python (Jamei et al 2023b, a). In this research, the ML model is optimized using the grid search technique.…”

Section: Lstm Layermentioning

confidence: 99%

Multistep Ahead Forecasting of Electrical Conductivity in Rivers by Using a Hybrid Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) Model Enhanced by Boruta-XGBoost Feature Selection Algorithm

Karbasi

Ali

Bateni

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Electrical conductivity (EC) is a key water quality metric for predicting the salinity and mineralization. In this study, the 10-day-ahead EC of two Australian rivers, Albert River and Barratta Creek, was forecasted using a novel deep learning algorithm, i.e., the convolutional neural network combined with long short-term memory (CNN-LSTM) model. The Boruta-extreme gradient boosting (XGBoost, XGB) feature selection method was used to determine the significant inputs (time series lagged data) for the model. The performance of the proposed Boruta-XGB-CNN-LSTM model was compared with those of three machine learning approaches: multi-layer perceptron neural network (MLP), K-nearest neighbor (KNN), and XGBoost, considering different statistical metrics such as the correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error (MAPE). Ten years of data for both rivers were extracted, with data for seven (2012–2018) and three years (2019–2021) used for training and testing the models, respectively. The Boruta-XGB-CNN-LSTM algorithm outperformed the other models in forecasting the 1-day-ahead EC in both stations over the test dataset (R = 0.9429, RMSE = 45.6896, and MAPE = 5.9749 for Albert River; and R = 0.9215, RMSE = 43.8315, and MAPE = 7.6029 for Barratta Creek). In addition, the Boruta-XGB-CNN-LSTM model could effectively forecast the EC for the next 3–10 days. Nevertheless, the performance of the Boruta-XGB-CNN-LSTM model slightly deteriorated as the forecasting horizon increased from 3 to 10 days. Overall, the Boruta-XGB-CNN-LSTM model is an effective soft computing method for accurately predicting the EC fluctuation in rivers.

show abstract

Development of a TVF-EMD-based multi-decomposition technique integrated with Encoder-Decoder-Bidirectional-LSTM for monthly rainfall forecasting

Cited by 20 publications

References 75 publications

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm

Mapping Forest Fire-affected Areas Using Advanced Machine Learning Techniques in Damoh District of Central India

Multistep Ahead Forecasting of Electrical Conductivity in Rivers by Using a Hybrid Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) Model Enhanced by Boruta-XGBoost Feature Selection Algorithm

Contact Info

Product

Resources

About